A method and system for realizing user identity recognition based on mobile phone sensor data

Through the differential analysis of mobile phone accelerometer and GPS data, a relational database is established, which solves the problem of difficult to judge drivers and passengers in the existing technology, and achieves high-precision user identity identification and accurate acquisition of driving behavior data.

CN114697873BActive Publication Date: 2024-11-12北京宏瓴科技发展有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210312754.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-28
Publication Date
2024-11-12
Estimated Expiration
2042-03-28

AI Technical Summary

Technical Problem

The prior art is difficult to accurately determine whether the driver or passenger is used to sense data by mobile phones, and it is impossible to effectively distinguish driving behavior data, resulting in low data utilization efficiency.

Method used

Through mobile phone accelerometer and GPS data testing, the difference in line speed and centrifugal acceleration of the vehicle when turning is calculated, a relational database is established, the data is compared to determine driving data or passenger data, and identity identification is achieved using pre-processing and comparison algorithms.

Benefits of technology

It realizes high-precision user identity identification based on mobile phone sensing data, ensuring the accuracy and effectiveness of driving behavior data without the need for other data sources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114697873B_ABST
    Figure CN114697873B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for realizing user identity recognition based on mobile phone sensor data, including obtaining travel data; preprocessing the travel data, calculating the linear speed and centrifugal acceleration value in actual driving according to the turning angle of the travel data, and comparing them with the corresponding values ​​in a pre-established relational database; and determining whether the travel data is driving data or passenger data by comparing the comparison result with a preset threshold. Through the above scheme, driving behavior can be identified directly based on the data collected by the mobile phone without the help of other data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for realizing user identity recognition based on mobile phone sensor data. Background Art

[0002] With the advent of the era of big data in the Internet of Vehicles, technologies such as big data and artificial intelligence can accurately describe the quality of user driving behavior. After collecting data on the speed, acceleration, temperature, pressure, brightness and other aspects of various vehicles, the Internet of Vehicles comprehensively analyzes the driver's operating status, the vehicle's own operating status and road conditions, and finally expresses them with accurate data.

[0003] Therefore, effective driving behavior data is the premise for analyzing the driver's driving habits. For the large amount of car networking driving trip data obtained, filtering out invalid and false data has always been a difficult point in data utilization, and it is also the focus of automobile OEMs and car networking technology companies. Conventional technology is difficult to distinguish between drivers and passengers through mobile phone sensor data, judge user driving behavior, and cannot distinguish who is driving through mobile phone apps. Summary of the invention

[0004] In order to solve the above-mentioned problems in the prior art, the present invention provides a method and system for realizing user identity recognition based on mobile phone sensor data, taking effective driving behavior data as the premise for analyzing the driver's driving habits, testing and calculating the differences in linear speed and centrifugal acceleration of the driver's seat and the passenger seat due to the different turning radius when the vehicle turns through the mobile phone accelerometer and GPS data, thereby analyzing whether the mobile phone is in the driver's seat or the passenger seat.

[0005] The present application provides a method for realizing user identity recognition based on mobile phone sensor data, the method comprising:

[0006] Get trip data;

[0007] Preprocessing the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with corresponding values ​​in a pre-established relational database;

[0008] By comparing the comparison result with a preset threshold, it is determined whether the travel data is driving data or passenger data.

[0009] Preferably, the pre-establishment of the relational database includes:

[0010] Use mobile phone accelerometers and GPS positioning systems to conduct road tests to obtain the linear speed and centrifugal acceleration of the driver and passenger seats of the vehicle when the vehicle is in different positions during the turning process;

[0011] The average and standard deviation of the centrifugal acceleration of the driver and passenger seats of the vehicle at different turning angles are calculated, and a relationship database of turning angle, linear speed and centrifugal acceleration is established.

[0012] Preferably, the travel data includes GPS point data and accelerometer data.

[0013] Furthermore, the preprocessing of the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with corresponding values ​​in a pre-established relational database includes:

[0014] Traverse all GPS data points in the trip data after correction;

[0015] Extract the turning angle and the average linear speed in the turning from the GPS point data to obtain several groups of GPS turning data;

[0016] Extracting centrifugal acceleration data from accelerometer data;

[0017] According to the start and end turning point timestamps of each group of GPS turning data, the centrifugal acceleration recorded by the accelerometer in the corresponding time period is found to obtain the average centrifugal acceleration of each group;

[0018] The average centrifugal acceleration is compared with the corresponding data in the relational database to determine whether the trip data is driving data or passenger data.

[0019] Further, the obtaining of several sets of GPS turn data includes:

[0020] S1 sorts the GPS point data in order of collection time and makes first-order difference of the azimuth angle data;

[0021] S2 searches for adjacent points with the same first-order difference sign one by one, and accumulates and sums the first-order differences as the turning angle;

[0022] S3 obtains the average linear speed during the turning process according to the timestamps and longitude and latitude of the starting and ending turning points;

[0023] S4 repeats steps S2 and S3 to obtain several sets of GPS turning data.

[0024] Furthermore, comparing the average centrifugal acceleration with corresponding data in the relational database to determine whether the travel data is driving data or passenger data includes:

[0025] a. Use GPS turn data as an index to find the closest turn angle in the relational database;

[0026] b. By comparing the linear speed and the average centrifugal acceleration at the same turning angle, determine whether the linear speed and the centrifugal acceleration of the travel data meet the constraint conditions; the travel data that meets the constraint conditions is determined as driving data, otherwise it is determined as passenger data;

[0027] c. Repeat steps a and b above for each set of turning data, and obtain the final result by weighting the turning time.

[0028] Furthermore, the constraints include:

[0029] (Database driving position linear speed - standard deviation) ≤ travel linear speed ≤ (database driving position linear speed + standard deviation);

[0030] (Database driving position centrifugal acceleration - standard deviation) ≤ stroke centrifugal acceleration ≤ (database driving position centrifugal acceleration + standard deviation).

[0031] A user identity recognition system based on driving behavior data, the system comprising:

[0032] Acquisition module, used to obtain travel data;

[0033] An online processing module, used for pre-processing the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with the corresponding values ​​in a pre-established relational database;

[0034] The determination module is used to determine whether the travel data is driving data or passenger data by comparing the comparison result with a preset threshold.

[0035] The beneficial effects of the present invention are embodied in:

[0036] The present invention provides a method and system for realizing user identity recognition based on mobile phone sensor data, which obtains travel data and pre-processes the travel data, calculates the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and compares them with the corresponding values ​​in a pre-established relational database; thereby determining driving data or passenger data. The travel data is obtained by collecting accelerometers and GPS positioning systems on the mobile phone, and driving behavior can be directly identified based on the data collected by the mobile phone without the help of other data. The differences in linear speed and centrifugal acceleration caused by different turning radii between the driver's seat and the passenger's seat when the vehicle turns are tested and calculated through the mobile phone accelerometer and GPS data, thereby analyzing whether the mobile phone is in the driver's seat or the passenger's seat.

[0037] Among them, the pre-constructed relational database is obtained through multiple real road test experiments, which can ensure the correlation between each turning angle and driving behavior contained in the relevant data of the relational database obtained based on the test experiment, and meet the requirements of high precision and high accuracy in the identity recognition of driving behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0039] Figure 1 A flow chart of a method for realizing user identity recognition based on mobile phone sensor data provided by the present invention;

[0040] Figure 2 A curve diagram showing the relationship between the curve angle and the linear speed provided by the present invention;

[0041] Figure 3 The present invention provides a curve diagram of the relationship between the bend angle and the centrifugal acceleration. DETAILED DESCRIPTION

[0042] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0043] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0044] Embodiment 1: The specific implementation of the present invention provides embodiment 1: a method for realizing user identity recognition based on mobile phone sensor data, such as Figure 1 As shown, the method includes:

[0045] S101 obtains travel data;

[0046] S102 pre-processes the travel data, calculates the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and compares them with corresponding values ​​in a pre-established relational database;

[0047] S103 determines whether the travel data is driving data or passenger data by comparing the comparison result with a preset threshold.

[0048] In step S101 , the acquired travel data includes GPS point data and accelerometer data.

[0049] Preprocess the trip data, calculate the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the trip data, and compare them with the corresponding values ​​in the pre-established relational database, including:

[0050] Traverse all GPS data points in the trip data after correction;

[0051] Extract the turning angle and the average linear speed in the turning from the GPS point data to obtain several groups of GPS turning data;

[0052] Extracting centrifugal acceleration data from accelerometer data;

[0053] According to the start and end turning point timestamps of each group of GPS turning data, the centrifugal acceleration recorded by the accelerometer in the corresponding time period is found to obtain the average centrifugal acceleration of each group;

[0054] The average centrifugal acceleration is compared with the corresponding data in the relational database to determine whether the trip data is driving data or passenger data.

[0055] Among them, several groups of GPS turn data are obtained including:

[0056] S1 sorts the GPS point data in order of collection time and makes first-order difference of the azimuth angle data;

[0057] S2 searches for adjacent points with the same first-order difference sign one by one, and accumulates and sums the first-order differences as the turning angle;

[0058] S3 obtains the average linear speed during the turning process according to the timestamps and longitude and latitude of the starting and ending turning points;

[0059] S4 repeats steps S2 and S3 to obtain several sets of GPS turning data.

[0060] Comparing the average centrifugal acceleration with the corresponding data in the relational database to determine whether the trip data is driving data or passenger data includes:

[0061] a. Use GPS turn data as an index to find the closest turn angle in the relational database;

[0062] b. By comparing the linear speed and the average centrifugal acceleration at the same turning angle, determine whether the linear speed and the centrifugal acceleration of the travel data meet the constraint conditions; the travel data that meets the constraint conditions is determined as driving data, otherwise it is determined as passenger data;

[0063] The constraint condition in step b is specifically shown in the following formula:

[0064] (Database driving position linear speed - standard deviation) ≤ travel linear speed ≤ (database driving position linear speed + standard deviation);

[0065] (Database driving position centrifugal acceleration - standard deviation) ≤ stroke centrifugal acceleration ≤ (database driving position centrifugal acceleration + standard deviation).

[0066] c. Repeat steps a and b above for each set of turning data, and obtain the final result by weighting the turning time.

[0067] In step S102, the pre-establishment of the relational database includes:

[0068] Use mobile phone accelerometers and GPS positioning systems to conduct road tests to obtain the linear speed and centrifugal acceleration of the driver and passenger seats of the vehicle when the vehicle is in different positions during the turning process;

[0069] The average and standard deviation of the centrifugal acceleration of the driver and passenger seats of the vehicle at different turning angles are calculated, and a relationship database of turning angle, linear speed and centrifugal acceleration is established.

[0070] The above method can be roughly divided into two parts in practical application. The first is road test experiment: using mobile phone accelerometer and GPS point data through multiple real road test experiments to obtain the linear speed, centrifugal acceleration and total turning angle of different positions of the vehicle during the turning process, and then statistically analyze them. The second is the online processing of trip data: when processing trip data, the linear speed and centrifugal acceleration values ​​when the data is real driving data are calculated according to the turning angle, and compared with the corresponding values ​​in the statistical data. If it does not exceed the comparison threshold, the data is determined to be driving data, otherwise it is passenger data.

[0071] 1. Road test experiment:

[0072] For curves of different angles, the linear speed and centrifugal acceleration of the vehicle driver's seat and passenger seat were tested multiple times, and the records were made into a table, as shown in Table 1 below. The average value and standard deviation were calculated to establish a database of the relationship between curve angle, linear speed, and centrifugal acceleration. Figure 2 and Figure 3 As shown, the curves of the relationship between the curve angle and the linear speed and the curve of the relationship between the curve angle and the centrifugal acceleration are drawn.

[0073] Table 1 Statistics of curve test records

[0074]

[0075] 2. Processing travel data online:

[0076] 201: Get the travel data of a mobile phone record in the database.

[0077] 202: Extract the turning angle and average linear speed during the turning process from the GPS point data. ① Sort the GPS points in ascending order of time, and make first-order differences in the direction angle data; ② Search for adjacent points with the same first-order difference sign one by one, and add and sum the first-order differences as the turning angle; ③ According to the timestamps and longitude and latitude of the start and end turning points, obtain the average linear speed during the turning process; ④ Repeat steps ②③ to obtain several sets of GPS turning data.

[0078] 203: Extract centrifugal acceleration data from the accelerometer data. According to the start and end turning point timestamps of each group obtained in 202, find the centrifugal acceleration recorded by the accelerometer in the corresponding time period to obtain the average centrifugal acceleration of each group.

[0079] 204: Compare each set of calculated turning data with the corresponding data in the database to determine whether the travel data is driving data or passenger data. ① Use the turning angle as an index to find the closest turning data in the database; ② Compare the linear speed and average centrifugal acceleration. If the linear speed and centrifugal acceleration of the travel data meet the following conditions:

[0080] (Database driving position linear speed - standard deviation) ≤ travel linear speed ≤ (database driving position linear speed + standard deviation)

[0081] (Database driving position centrifugal acceleration - standard deviation) ≤ stroke centrifugal acceleration ≤ (database driving position centrifugal acceleration + standard deviation)

[0082] The trip data is determined to be driving data, otherwise it is passenger data.

[0083] ③ Repeat the above steps ① and ② for each set of turning data, and finally obtain the final result by weighting according to the turning time.

[0084] Embodiment 2: Based on the same technical concept, Embodiment 2 of the present invention further provides a system for realizing user identity recognition based on mobile phone sensor data, the system comprising:

[0085] Acquisition module, used to obtain travel data;

[0086] An online processing module, used for pre-processing the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with the corresponding values ​​in a pre-established relational database;

[0087] The determination module is used to determine whether the travel data is driving data or passenger data by comparing the comparison result with a preset threshold.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for realizing user identity recognition based on mobile phone sensor data, characterized in that: The method comprises: Get trip data, including GPS point data and accelerometer data; Preprocessing the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with corresponding values ​​in a pre-established relational database; By comparing the comparison result with a preset threshold, determining whether the trip data is driving data or passenger data; The preprocessing of the travel data, calculating the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and comparing them with the corresponding values ​​in the pre-established relational database includes: Traverse all GPS data points in the trip data after correction; Extract the turning angle and the average linear speed in the turning from the GPS point data to obtain several groups of GPS turning data; Extracting centrifugal acceleration data from accelerometer data; According to the start and end turning point timestamps of each group of GPS turning data, the centrifugal acceleration recorded by the accelerometer in the corresponding time period is found to obtain the average centrifugal acceleration of each group; Comparing the average centrifugal acceleration with corresponding data in the relational database to determine whether the trip data is driving data or passenger data; The comparing the average centrifugal acceleration with the corresponding data in the relational database to determine whether the travel data is driving data or passenger data includes: a. Use GPS turn data as an index to find the closest turn angle in the relational database; b. By comparing the linear speed and the average centrifugal acceleration at the same turning angle, determine whether the linear speed and the centrifugal acceleration of the travel data meet the constraint conditions; the travel data that meets the constraint conditions is determined as driving data, otherwise it is determined as passenger data; c. Repeat steps a and b above for each set of turning data, and obtain the final result by weighting according to the turning time; The constraints include: (Database driving position linear speed - standard deviation) ≤ travel linear speed ≤ (database driving position linear speed + standard deviation); (Database driving position centrifugal acceleration - standard deviation) ≤ stroke centrifugal acceleration ≤ (database driving position centrifugal acceleration + standard deviation).

2. The method according to claim 1, characterized in that The pre-establishment of the relational database includes: Use mobile phone accelerometers and GPS positioning systems to conduct road tests to obtain the linear speed and centrifugal acceleration of the driver and passenger seats of the vehicle when the vehicle is in different positions during the turning process; The average and standard deviation of the centrifugal acceleration of the driver and passenger seats of the vehicle at different turning angles are calculated, and a relationship database of turning angle, linear speed and centrifugal acceleration is established.

3. The method according to claim 1, characterized in that: The obtaining of several sets of GPS turn data includes: S1 sorts the GPS point data in order of collection time and makes first-order difference of the azimuth angle data; S2 searches for adjacent points with the same first-order difference sign one by one, and accumulates and sums the first-order differences as the turning angle; S3 obtains the average linear speed during the turning process according to the timestamps and longitude and latitude of the starting and ending turning points; S4 repeats steps S2 and S3 to obtain several sets of GPS turning data.

4. A system for realizing user identity recognition based on mobile phone sensor data, characterized in that: The system comprises: The acquisition module is used to obtain the travel data, including GPS point data and accelerometer data; An online processing module is used to pre-process the travel data, calculate the linear speed and centrifugal acceleration values ​​in actual driving according to the turning angle of the travel data, and compare them with the corresponding values ​​in a pre-established relational database; A determination module, used to determine whether the trip data is driving data or passenger data by comparing the comparison result with a preset threshold; The online processing module is specifically used for: Traverse all GPS data points in the trip data after correction; Extract the turning angle and the average linear speed in the turning from the GPS point data to obtain several groups of GPS turning data; Extracting centrifugal acceleration data from accelerometer data; According to the start and end turning point timestamps of each group of GPS turning data, the centrifugal acceleration recorded by the accelerometer in the corresponding time period is found to obtain the average centrifugal acceleration of each group; Comparing the average centrifugal acceleration with corresponding data in the relational database to determine whether the trip data is driving data or passenger data; The determination module is specifically used for: Use GPS turn data as an index to find the closest turn angle in the relational database; By comparing the linear speed and the average centrifugal acceleration at the same turning angle, it is determined whether the linear speed and the centrifugal acceleration of the travel data meet the constraint conditions; the travel data that meets the constraint conditions is determined as driving data, otherwise it is determined as passenger data; For each set of turning data, repeat steps a and b above, and weight them according to the turning time to get the final result; The constraints include: (Database driving position linear speed - standard deviation) ≤ travel linear speed ≤ (database driving position linear speed + standard deviation); (Database driving position centrifugal acceleration - standard deviation) ≤ stroke centrifugal acceleration ≤ (database driving position centrifugal acceleration + standard deviation).